Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 740 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1198175 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1283832 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.4299. Min Act: -0.0000

Data Index: 183668 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3673. Min Act: -0.0000

Data Index: 630048 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3344. Min Act: -0.0000

Data Index: 669411 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.4176. Min Act: -0.0000

Data Index: 379027 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.4188. Min Act: -0.0000

Data Index: 706570 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.4209. Min Act: -0.0000

Data Index: 136328 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.4214. Min Act: -0.0000

Data Index: 935205 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3742. Min Act: -0.0000

Data Index: 596196 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3466. Min Act: -0.0000

Data Index: 513744 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3765. Min Act: -0.0000

Data Index: 609282 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3905. Min Act: -0.0000

Data Index: 99242 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3711. Min Act: -0.0000

Data Index: 827270 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3772. Min Act: -0.0000

Data Index: 706705 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.2960. Min Act: -0.0000

Data Index: 1048068 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3809. Min Act: -0.0000

Data Index: 47846 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3548. Min Act: -0.0000

Data Index: 246055 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3274. Min Act: -0.0000

Data Index: 1162891 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3655. Min Act: -0.0000

Data Index: 14720 (C4 (Web Text))

Max Activating Token Index: 220